On quick word spotting techniques
- 24 March 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
This paper describes 2 efficiency enhancements for speaker-independent connected spoken word spotting. The first enhancement, LESS COST, uses phoneme concatenation to reduce the cost of computing the local distance between each reference and input pattern point. The second enhancement, Coarse DP refinement, reduces the cost of dynamic time warping for only a small error rate penalty. An experiment confirmed these techniques.Keywords
This publication has 2 references indexed in Scilit:
- Connected spoken word recognition algorithms by constant time delay DP, O(n) DP and augmented continuous DP matchingInformation Sciences, 1984
- Detecting and locating key words in continuous speech using linear predictive codingIEEE Transactions on Acoustics, Speech, and Signal Processing, 1977